Channel
@MadML_Talks
On this record: Growth · Engagement · Reactions · Posts · Citations · Cite this entry
277subscribers
-1 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1002498655132 |
|---|---|
| Type | Channel |
| Username | @MadML_Talks |
| Created | Between 1 October 2024 and 31 March 2025— estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 6 August 2026 |
| Last confirmed live | 7 August 2026 |
| Measurements held | 3 |
| Confirmed unchanged | 1 time, most recently 7 August 2026 |
| On Telegram | t.me/MadML_Talks |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 7 Aug 2026, 05:30 | 277 | -1 |
| 6 Aug 2026, 23:31 | 278 | no change |
| 6 Aug 2026, 08:00 | 278 | first reading |
17 posts held, back to 28 July 2025 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 17 posts for this entry, the most recent from 8 January 2026. An engagement rate over an empty window would be a number about nothing.
136 reactions across 14 posts, in 13 distinct kinds. The most used accounts for 62.5% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 🔥 | 85 | 62.5% | |
| ❤ | 22 | 16.2% | |
| 🤓 | 8 | 5.88% | |
| 👍 | 5 | 3.68% | |
| 😱 | 3 | 2.21% | |
| ⚡ | 2 | 1.47% | |
| ✍ | 2 | 1.47% | |
| ❤🔥 | 2 | 1.47% | |
| 🤔 | 2 | 1.47% | |
| 🤝 | 2 | 1.47% | |
| 🏆 | 1 | 0.735% | |
| 💯 | 1 | 0.735% | |
| 🙏 | 1 | 0.735% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 14 of the 17 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 136reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 17 most recent posts we hold, published 28 July 2025 to 8 January 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
В конце прошлого года OpenAI анонсировала Apps SDK, а позже открыла возможность регистрации собственных приложений. Что это дает? Теперь вы можете создавать собственные приложения, разворачивая MCP серверы, и регистрировать их в OpenAI и тогда любой пользователь ChatGPT сможет подключать их (или триггерить специальными фразами) и обращаться к вашему серверу. Уже сейчас магазин приложений достаточно широк и вы можете …
🔥3😱3✍2👍1
Photo, posted without a caption
Материалы встречи 4.12.2025 Спикер: Владислав Попов, Machine Learning Engineer Доклад "TnT-LLM: Text Mining at Scale with Large Language Models" Запись на YouTube: https://youtu.be/FY3VevXMuw8?si=DDKUoKpYielvQyF0 Ссылка на статью, которую обсуждали на встрече: https://arxiv.org/abs/2403.12173v1 Дополнительные материалы: https://docs.boundaryml.com/home
❤5🔥3🤓1
TnT-LLM: Text Mining at Scale with Large Language Models Разметка больших текстовых корпусов вручную занимает недели и почти не масштабируется. В этом докладе мы покажем TnT-LLM — фреймворк на базе больших языковых моделей, который автоматически строит иерархии меток и создаёт псевдоразметку. Разберём, как двухэтапный подход (генерация таксономии → разметка текста) позволяет ускорить создание классификаторов и обсу…
❤5🤓4🔥3
Материалы встречи 6.11.2025 Спикер: Алина Бурыкина, Machine Learning Engineer, Mad Devs Доклад: Intro to Contrastive Learning: теория, интуиция и современные подходы Запись на YouTube: https://www.youtube.com/watch?v=HCb0VNpjGCM
🔥5❤1🏆1
Intro to Contrastive Learning: теория, интуиция и современные подходы Контрастивное обучение стало краеугольным камнем современных self-supervised методов в компьютерном зрении и за его пределами. В этом докладе мы разберём ключевые идеи, лежащие в основе подхода — от информационно-теоретических принципов (взаимная информация, InfoNCE) до практических реализаций. Рассмотрим классические методы с отрицательными прим…
🔥7⚡2
Запись доклада доступна по ссылке: https://www.youtube.com/watch?v=0XhFB9OItqw 🚀
❤7🔥6❤🔥1🙏1
Презентация сегодняшнего доклада
🔥10🤝2
Через 10 минут начинаем
Schema-guided reasoning: как заставить LLM быть умнее. В докладе рассмотрим SGR подход, который повышает бизнес-метрики и заставляет ризонить модели не обученные для этого. Возможно, вы уже использовали этот подход, но не знали об этом. Так же рассмотрим плюсы и минусы SGR и посмотрим, как собрать LLM агента без специальных фреймворков практически на чистом OpenAI SDK. Сложность 3/10. Спикер: Александр Брыль, ML и…
🔥7❤🔥1👍1
А вы замечали, что ЛЛМ могут быть не особо разнообразны в своих генерациях? Все мы знаем, что уже давно принято добавлять синтетические данные для обучения новых моделей. Это дешевле, безопаснее, решает проблему регуляризации и репрезентации (аугментирование данных). Именно с одной из таких проблем мы столкнулись в работе. Нам необходимо было построить модель классификации, которая бы относила пользовательский запр…
🤔2👍1
Sonar Embedding Space и Large Concept Model (LCM): от универсального пространства представлений к работе с абстрактными понятиями В этом докладе мы разберём две связанные работы — Sonar Embedding Space и Large Concept Model (LCM). Обе статьи поднимают вопрос: как моделям лучше захватывать и организовывать знания. Sonar предлагает единое встраиваемое пространство, где тексты и другие модальности сопоставляются напрям…
🔥6🤓1
Showing the 12 most recent of 17 posts we hold for @MadML_Talks. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Citation-graph rank — 296,649 of 1,176,251entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 7 August 2026 — this entry's latest reading, not the date you are reading this.
“MadML 🚀” (@MadML_Talks), 277 subscribers as measured 7 August 2026. Telegram Register, tgregister.com/channel/MadML_Talks.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.